Abstract
We present a deep prototype-based learning architecture which achieves a performance that is competitive to a conventional, shallow prototype-based model but at a fraction of the computational cost, especially w.r.t. memory requirements. As prototype-based classification and regression methods are typically plagued by the exploding number of prototypes necessary to solve complex problems, this is an important step towards efficient prototype-based classification and regression. We demonstrate these claims by benchmarking our deep prototype-based model on the well-known MNIST dataset.
A. Gepperth—Thomas Hecht gratefully acknowledges funding support by the “Direction Générale de l’Armement” (DGA) and Ecole Polytechnique.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rosch, E.: Cognitive reference points. Cogn. Psychol. 7, 532–547 (1975)
Biehl, M., Ghosh, A., Hammer, B.: Dynamics and generalization ability of LVQ algorithms. J. Mach. Learn. Res. 8, 323–360 (2007)
Moody, J., Darken, C.J.: Fast learning in networks of locally tuned processing units. Neural Comput. 1, 281–294 (1989)
Kohonen, T.: Self-organized formation of topologically correct feature maps. Biol. Cybern. 43, 59–69 (1982)
Arulampalam, M.S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear, non-Gaussian Bayesian tracking. IEEE Trans. Sig. Process. 50(2), 174–188 (2002)
Losing, V., Hammer, B., Wersing, H.: Interactive online learning for obstacle classification on a mobile robot. In: IEEE (2015)
Gepperth, A., Karaoguz, C.: A bio-inspired incremental learning architecture for applied perceptual problems. Cogn. Comput. (2015, accepted)
Gepperth, A., Hammer, B.: Incremental learning algorithms and applications. In: European Sympoisum on Artificial Neural Networks (ESANN) (2016)
Carse, B., Fogarty, T.C.: Tackling the “curse of dimensionality” of radial basis functional neural networks using a genetic algorithm. In: Voigt, H.-M., Ebeling, W., Rechenberg, I., Schwefei, H.-P. (eds.) Parallel Problem Solving from Nature – PPSN IV. LNCS, pp. 707–719. Springer, Heidelberg (1996)
Sermanet, P., Kavukcuoglu, K., Chintala, S., LeCun, Y.: Pedestrian detection with unsupervised multi-stage feature learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3626–3633 (2013)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Schneider, P., Biehl, M., Hammer, B.: Hyperparameter learning in probabilistic prototype-based models. Neurocomputing 73(7–9), 1117–1124 (2010). Advances in Computational Intelligence and Learning 17th European Symposium on Artificial Neural Networks 2009
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Hecht, T., Gepperth, A. (2016). Computational Advantages of Deep Prototype-Based Learning. In: Villa, A., Masulli, P., Pons Rivero, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2016. ICANN 2016. Lecture Notes in Computer Science(), vol 9887. Springer, Cham. https://doi.org/10.1007/978-3-319-44781-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-44781-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44780-3
Online ISBN: 978-3-319-44781-0
eBook Packages: Computer ScienceComputer Science (R0)